mirror of
https://github.com/facebook/rocksdb.git
synced 2024-11-28 15:33:54 +00:00
249eff0f30
Summary: Since read threads do not coordinate on loading data into block cache, two threads between Lookup and Insert can end up loading and inserting the same data. This is particularly concerning with cache_index_and_filter_blocks since those are hot and more likely to be race targets if ejected from (or not pre-populated in) the cache. Particularly with moves toward disaggregated / network storage, the cost of redundant retrieval might be high, and we should at least have some hard statistics from which we can estimate impact. Example with full filter thrashing "cliff": $ ./db_bench --benchmarks=fillrandom --num=15000000 --cache_index_and_filter_blocks -bloom_bits=10 ... $ ./db_bench --db=/tmp/rocksdbtest-172704/dbbench --use_existing_db --benchmarks=readrandom,stats --num=200000 --cache_index_and_filter_blocks --cache_size=$((130 * 1024 * 1024)) --bloom_bits=10 --threads=16 -statistics 2>&1 | egrep '^rocksdb.block.cache.(.*add|.*redundant)' | grep -v compress | sort rocksdb.block.cache.add COUNT : 14181 rocksdb.block.cache.add.failures COUNT : 0 rocksdb.block.cache.add.redundant COUNT : 476 rocksdb.block.cache.data.add COUNT : 12749 rocksdb.block.cache.data.add.redundant COUNT : 18 rocksdb.block.cache.filter.add COUNT : 1003 rocksdb.block.cache.filter.add.redundant COUNT : 217 rocksdb.block.cache.index.add COUNT : 429 rocksdb.block.cache.index.add.redundant COUNT : 241 $ ./db_bench --db=/tmp/rocksdbtest-172704/dbbench --use_existing_db --benchmarks=readrandom,stats --num=200000 --cache_index_and_filter_blocks --cache_size=$((120 * 1024 * 1024)) --bloom_bits=10 --threads=16 -statistics 2>&1 | egrep '^rocksdb.block.cache.(.*add|.*redundant)' | grep -v compress | sort rocksdb.block.cache.add COUNT : 1182223 rocksdb.block.cache.add.failures COUNT : 0 rocksdb.block.cache.add.redundant COUNT : 302728 rocksdb.block.cache.data.add COUNT : 31425 rocksdb.block.cache.data.add.redundant COUNT : 12 rocksdb.block.cache.filter.add COUNT : 795455 rocksdb.block.cache.filter.add.redundant COUNT : 130238 rocksdb.block.cache.index.add COUNT : 355343 rocksdb.block.cache.index.add.redundant COUNT : 172478 Pull Request resolved: https://github.com/facebook/rocksdb/pull/6681 Test Plan: Some manual testing (above) and unit test covering key metrics is included Reviewed By: ltamasi Differential Revision: D21134113 Pulled By: pdillinger fbshipit-source-id: c11497b5f00f4ffdfe919823904e52d0a1a91d87
415 lines
19 KiB
C++
415 lines
19 KiB
C++
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
|
|
// This source code is licensed under both the GPLv2 (found in the
|
|
// COPYING file in the root directory) and Apache 2.0 License
|
|
// (found in the LICENSE.Apache file in the root directory).
|
|
//
|
|
#include "monitoring/statistics.h"
|
|
|
|
#include <algorithm>
|
|
#include <cinttypes>
|
|
#include <cstdio>
|
|
#include "port/likely.h"
|
|
#include "rocksdb/statistics.h"
|
|
|
|
namespace ROCKSDB_NAMESPACE {
|
|
|
|
// The order of items listed in Tickers should be the same as
|
|
// the order listed in TickersNameMap
|
|
const std::vector<std::pair<Tickers, std::string>> TickersNameMap = {
|
|
{BLOCK_CACHE_MISS, "rocksdb.block.cache.miss"},
|
|
{BLOCK_CACHE_HIT, "rocksdb.block.cache.hit"},
|
|
{BLOCK_CACHE_ADD, "rocksdb.block.cache.add"},
|
|
{BLOCK_CACHE_ADD_FAILURES, "rocksdb.block.cache.add.failures"},
|
|
{BLOCK_CACHE_INDEX_MISS, "rocksdb.block.cache.index.miss"},
|
|
{BLOCK_CACHE_INDEX_HIT, "rocksdb.block.cache.index.hit"},
|
|
{BLOCK_CACHE_INDEX_ADD, "rocksdb.block.cache.index.add"},
|
|
{BLOCK_CACHE_INDEX_BYTES_INSERT, "rocksdb.block.cache.index.bytes.insert"},
|
|
{BLOCK_CACHE_INDEX_BYTES_EVICT, "rocksdb.block.cache.index.bytes.evict"},
|
|
{BLOCK_CACHE_FILTER_MISS, "rocksdb.block.cache.filter.miss"},
|
|
{BLOCK_CACHE_FILTER_HIT, "rocksdb.block.cache.filter.hit"},
|
|
{BLOCK_CACHE_FILTER_ADD, "rocksdb.block.cache.filter.add"},
|
|
{BLOCK_CACHE_FILTER_BYTES_INSERT,
|
|
"rocksdb.block.cache.filter.bytes.insert"},
|
|
{BLOCK_CACHE_FILTER_BYTES_EVICT, "rocksdb.block.cache.filter.bytes.evict"},
|
|
{BLOCK_CACHE_DATA_MISS, "rocksdb.block.cache.data.miss"},
|
|
{BLOCK_CACHE_DATA_HIT, "rocksdb.block.cache.data.hit"},
|
|
{BLOCK_CACHE_DATA_ADD, "rocksdb.block.cache.data.add"},
|
|
{BLOCK_CACHE_DATA_BYTES_INSERT, "rocksdb.block.cache.data.bytes.insert"},
|
|
{BLOCK_CACHE_BYTES_READ, "rocksdb.block.cache.bytes.read"},
|
|
{BLOCK_CACHE_BYTES_WRITE, "rocksdb.block.cache.bytes.write"},
|
|
{BLOOM_FILTER_USEFUL, "rocksdb.bloom.filter.useful"},
|
|
{BLOOM_FILTER_FULL_POSITIVE, "rocksdb.bloom.filter.full.positive"},
|
|
{BLOOM_FILTER_FULL_TRUE_POSITIVE,
|
|
"rocksdb.bloom.filter.full.true.positive"},
|
|
{BLOOM_FILTER_MICROS, "rocksdb.bloom.filter.micros"},
|
|
{PERSISTENT_CACHE_HIT, "rocksdb.persistent.cache.hit"},
|
|
{PERSISTENT_CACHE_MISS, "rocksdb.persistent.cache.miss"},
|
|
{SIM_BLOCK_CACHE_HIT, "rocksdb.sim.block.cache.hit"},
|
|
{SIM_BLOCK_CACHE_MISS, "rocksdb.sim.block.cache.miss"},
|
|
{MEMTABLE_HIT, "rocksdb.memtable.hit"},
|
|
{MEMTABLE_MISS, "rocksdb.memtable.miss"},
|
|
{GET_HIT_L0, "rocksdb.l0.hit"},
|
|
{GET_HIT_L1, "rocksdb.l1.hit"},
|
|
{GET_HIT_L2_AND_UP, "rocksdb.l2andup.hit"},
|
|
{COMPACTION_KEY_DROP_NEWER_ENTRY, "rocksdb.compaction.key.drop.new"},
|
|
{COMPACTION_KEY_DROP_OBSOLETE, "rocksdb.compaction.key.drop.obsolete"},
|
|
{COMPACTION_KEY_DROP_RANGE_DEL, "rocksdb.compaction.key.drop.range_del"},
|
|
{COMPACTION_KEY_DROP_USER, "rocksdb.compaction.key.drop.user"},
|
|
{COMPACTION_RANGE_DEL_DROP_OBSOLETE,
|
|
"rocksdb.compaction.range_del.drop.obsolete"},
|
|
{COMPACTION_OPTIMIZED_DEL_DROP_OBSOLETE,
|
|
"rocksdb.compaction.optimized.del.drop.obsolete"},
|
|
{COMPACTION_CANCELLED, "rocksdb.compaction.cancelled"},
|
|
{NUMBER_KEYS_WRITTEN, "rocksdb.number.keys.written"},
|
|
{NUMBER_KEYS_READ, "rocksdb.number.keys.read"},
|
|
{NUMBER_KEYS_UPDATED, "rocksdb.number.keys.updated"},
|
|
{BYTES_WRITTEN, "rocksdb.bytes.written"},
|
|
{BYTES_READ, "rocksdb.bytes.read"},
|
|
{NUMBER_DB_SEEK, "rocksdb.number.db.seek"},
|
|
{NUMBER_DB_NEXT, "rocksdb.number.db.next"},
|
|
{NUMBER_DB_PREV, "rocksdb.number.db.prev"},
|
|
{NUMBER_DB_SEEK_FOUND, "rocksdb.number.db.seek.found"},
|
|
{NUMBER_DB_NEXT_FOUND, "rocksdb.number.db.next.found"},
|
|
{NUMBER_DB_PREV_FOUND, "rocksdb.number.db.prev.found"},
|
|
{ITER_BYTES_READ, "rocksdb.db.iter.bytes.read"},
|
|
{NO_FILE_CLOSES, "rocksdb.no.file.closes"},
|
|
{NO_FILE_OPENS, "rocksdb.no.file.opens"},
|
|
{NO_FILE_ERRORS, "rocksdb.no.file.errors"},
|
|
{STALL_L0_SLOWDOWN_MICROS, "rocksdb.l0.slowdown.micros"},
|
|
{STALL_MEMTABLE_COMPACTION_MICROS, "rocksdb.memtable.compaction.micros"},
|
|
{STALL_L0_NUM_FILES_MICROS, "rocksdb.l0.num.files.stall.micros"},
|
|
{STALL_MICROS, "rocksdb.stall.micros"},
|
|
{DB_MUTEX_WAIT_MICROS, "rocksdb.db.mutex.wait.micros"},
|
|
{RATE_LIMIT_DELAY_MILLIS, "rocksdb.rate.limit.delay.millis"},
|
|
{NO_ITERATORS, "rocksdb.num.iterators"},
|
|
{NUMBER_MULTIGET_CALLS, "rocksdb.number.multiget.get"},
|
|
{NUMBER_MULTIGET_KEYS_READ, "rocksdb.number.multiget.keys.read"},
|
|
{NUMBER_MULTIGET_BYTES_READ, "rocksdb.number.multiget.bytes.read"},
|
|
{NUMBER_FILTERED_DELETES, "rocksdb.number.deletes.filtered"},
|
|
{NUMBER_MERGE_FAILURES, "rocksdb.number.merge.failures"},
|
|
{BLOOM_FILTER_PREFIX_CHECKED, "rocksdb.bloom.filter.prefix.checked"},
|
|
{BLOOM_FILTER_PREFIX_USEFUL, "rocksdb.bloom.filter.prefix.useful"},
|
|
{NUMBER_OF_RESEEKS_IN_ITERATION, "rocksdb.number.reseeks.iteration"},
|
|
{GET_UPDATES_SINCE_CALLS, "rocksdb.getupdatessince.calls"},
|
|
{BLOCK_CACHE_COMPRESSED_MISS, "rocksdb.block.cachecompressed.miss"},
|
|
{BLOCK_CACHE_COMPRESSED_HIT, "rocksdb.block.cachecompressed.hit"},
|
|
{BLOCK_CACHE_COMPRESSED_ADD, "rocksdb.block.cachecompressed.add"},
|
|
{BLOCK_CACHE_COMPRESSED_ADD_FAILURES,
|
|
"rocksdb.block.cachecompressed.add.failures"},
|
|
{WAL_FILE_SYNCED, "rocksdb.wal.synced"},
|
|
{WAL_FILE_BYTES, "rocksdb.wal.bytes"},
|
|
{WRITE_DONE_BY_SELF, "rocksdb.write.self"},
|
|
{WRITE_DONE_BY_OTHER, "rocksdb.write.other"},
|
|
{WRITE_TIMEDOUT, "rocksdb.write.timeout"},
|
|
{WRITE_WITH_WAL, "rocksdb.write.wal"},
|
|
{COMPACT_READ_BYTES, "rocksdb.compact.read.bytes"},
|
|
{COMPACT_WRITE_BYTES, "rocksdb.compact.write.bytes"},
|
|
{FLUSH_WRITE_BYTES, "rocksdb.flush.write.bytes"},
|
|
{NUMBER_DIRECT_LOAD_TABLE_PROPERTIES,
|
|
"rocksdb.number.direct.load.table.properties"},
|
|
{NUMBER_SUPERVERSION_ACQUIRES, "rocksdb.number.superversion_acquires"},
|
|
{NUMBER_SUPERVERSION_RELEASES, "rocksdb.number.superversion_releases"},
|
|
{NUMBER_SUPERVERSION_CLEANUPS, "rocksdb.number.superversion_cleanups"},
|
|
{NUMBER_BLOCK_COMPRESSED, "rocksdb.number.block.compressed"},
|
|
{NUMBER_BLOCK_DECOMPRESSED, "rocksdb.number.block.decompressed"},
|
|
{NUMBER_BLOCK_NOT_COMPRESSED, "rocksdb.number.block.not_compressed"},
|
|
{MERGE_OPERATION_TOTAL_TIME, "rocksdb.merge.operation.time.nanos"},
|
|
{FILTER_OPERATION_TOTAL_TIME, "rocksdb.filter.operation.time.nanos"},
|
|
{ROW_CACHE_HIT, "rocksdb.row.cache.hit"},
|
|
{ROW_CACHE_MISS, "rocksdb.row.cache.miss"},
|
|
{READ_AMP_ESTIMATE_USEFUL_BYTES, "rocksdb.read.amp.estimate.useful.bytes"},
|
|
{READ_AMP_TOTAL_READ_BYTES, "rocksdb.read.amp.total.read.bytes"},
|
|
{NUMBER_RATE_LIMITER_DRAINS, "rocksdb.number.rate_limiter.drains"},
|
|
{NUMBER_ITER_SKIP, "rocksdb.number.iter.skip"},
|
|
{BLOB_DB_NUM_PUT, "rocksdb.blobdb.num.put"},
|
|
{BLOB_DB_NUM_WRITE, "rocksdb.blobdb.num.write"},
|
|
{BLOB_DB_NUM_GET, "rocksdb.blobdb.num.get"},
|
|
{BLOB_DB_NUM_MULTIGET, "rocksdb.blobdb.num.multiget"},
|
|
{BLOB_DB_NUM_SEEK, "rocksdb.blobdb.num.seek"},
|
|
{BLOB_DB_NUM_NEXT, "rocksdb.blobdb.num.next"},
|
|
{BLOB_DB_NUM_PREV, "rocksdb.blobdb.num.prev"},
|
|
{BLOB_DB_NUM_KEYS_WRITTEN, "rocksdb.blobdb.num.keys.written"},
|
|
{BLOB_DB_NUM_KEYS_READ, "rocksdb.blobdb.num.keys.read"},
|
|
{BLOB_DB_BYTES_WRITTEN, "rocksdb.blobdb.bytes.written"},
|
|
{BLOB_DB_BYTES_READ, "rocksdb.blobdb.bytes.read"},
|
|
{BLOB_DB_WRITE_INLINED, "rocksdb.blobdb.write.inlined"},
|
|
{BLOB_DB_WRITE_INLINED_TTL, "rocksdb.blobdb.write.inlined.ttl"},
|
|
{BLOB_DB_WRITE_BLOB, "rocksdb.blobdb.write.blob"},
|
|
{BLOB_DB_WRITE_BLOB_TTL, "rocksdb.blobdb.write.blob.ttl"},
|
|
{BLOB_DB_BLOB_FILE_BYTES_WRITTEN, "rocksdb.blobdb.blob.file.bytes.written"},
|
|
{BLOB_DB_BLOB_FILE_BYTES_READ, "rocksdb.blobdb.blob.file.bytes.read"},
|
|
{BLOB_DB_BLOB_FILE_SYNCED, "rocksdb.blobdb.blob.file.synced"},
|
|
{BLOB_DB_BLOB_INDEX_EXPIRED_COUNT,
|
|
"rocksdb.blobdb.blob.index.expired.count"},
|
|
{BLOB_DB_BLOB_INDEX_EXPIRED_SIZE, "rocksdb.blobdb.blob.index.expired.size"},
|
|
{BLOB_DB_BLOB_INDEX_EVICTED_COUNT,
|
|
"rocksdb.blobdb.blob.index.evicted.count"},
|
|
{BLOB_DB_BLOB_INDEX_EVICTED_SIZE, "rocksdb.blobdb.blob.index.evicted.size"},
|
|
{BLOB_DB_GC_NUM_FILES, "rocksdb.blobdb.gc.num.files"},
|
|
{BLOB_DB_GC_NUM_NEW_FILES, "rocksdb.blobdb.gc.num.new.files"},
|
|
{BLOB_DB_GC_FAILURES, "rocksdb.blobdb.gc.failures"},
|
|
{BLOB_DB_GC_NUM_KEYS_OVERWRITTEN, "rocksdb.blobdb.gc.num.keys.overwritten"},
|
|
{BLOB_DB_GC_NUM_KEYS_EXPIRED, "rocksdb.blobdb.gc.num.keys.expired"},
|
|
{BLOB_DB_GC_NUM_KEYS_RELOCATED, "rocksdb.blobdb.gc.num.keys.relocated"},
|
|
{BLOB_DB_GC_BYTES_OVERWRITTEN, "rocksdb.blobdb.gc.bytes.overwritten"},
|
|
{BLOB_DB_GC_BYTES_EXPIRED, "rocksdb.blobdb.gc.bytes.expired"},
|
|
{BLOB_DB_GC_BYTES_RELOCATED, "rocksdb.blobdb.gc.bytes.relocated"},
|
|
{BLOB_DB_FIFO_NUM_FILES_EVICTED, "rocksdb.blobdb.fifo.num.files.evicted"},
|
|
{BLOB_DB_FIFO_NUM_KEYS_EVICTED, "rocksdb.blobdb.fifo.num.keys.evicted"},
|
|
{BLOB_DB_FIFO_BYTES_EVICTED, "rocksdb.blobdb.fifo.bytes.evicted"},
|
|
{TXN_PREPARE_MUTEX_OVERHEAD, "rocksdb.txn.overhead.mutex.prepare"},
|
|
{TXN_OLD_COMMIT_MAP_MUTEX_OVERHEAD,
|
|
"rocksdb.txn.overhead.mutex.old.commit.map"},
|
|
{TXN_DUPLICATE_KEY_OVERHEAD, "rocksdb.txn.overhead.duplicate.key"},
|
|
{TXN_SNAPSHOT_MUTEX_OVERHEAD, "rocksdb.txn.overhead.mutex.snapshot"},
|
|
{TXN_GET_TRY_AGAIN, "rocksdb.txn.get.tryagain"},
|
|
{NUMBER_MULTIGET_KEYS_FOUND, "rocksdb.number.multiget.keys.found"},
|
|
{NO_ITERATOR_CREATED, "rocksdb.num.iterator.created"},
|
|
{NO_ITERATOR_DELETED, "rocksdb.num.iterator.deleted"},
|
|
{BLOCK_CACHE_COMPRESSION_DICT_MISS,
|
|
"rocksdb.block.cache.compression.dict.miss"},
|
|
{BLOCK_CACHE_COMPRESSION_DICT_HIT,
|
|
"rocksdb.block.cache.compression.dict.hit"},
|
|
{BLOCK_CACHE_COMPRESSION_DICT_ADD,
|
|
"rocksdb.block.cache.compression.dict.add"},
|
|
{BLOCK_CACHE_COMPRESSION_DICT_BYTES_INSERT,
|
|
"rocksdb.block.cache.compression.dict.bytes.insert"},
|
|
{BLOCK_CACHE_COMPRESSION_DICT_BYTES_EVICT,
|
|
"rocksdb.block.cache.compression.dict.bytes.evict"},
|
|
{BLOCK_CACHE_ADD_REDUNDANT, "rocksdb.block.cache.add.redundant"},
|
|
{BLOCK_CACHE_INDEX_ADD_REDUNDANT,
|
|
"rocksdb.block.cache.index.add.redundant"},
|
|
{BLOCK_CACHE_FILTER_ADD_REDUNDANT,
|
|
"rocksdb.block.cache.filter.add.redundant"},
|
|
{BLOCK_CACHE_DATA_ADD_REDUNDANT, "rocksdb.block.cache.data.add.redundant"},
|
|
{BLOCK_CACHE_COMPRESSION_DICT_ADD_REDUNDANT,
|
|
"rocksdb.block.cache.compression.dict.add.redundant"},
|
|
};
|
|
|
|
const std::vector<std::pair<Histograms, std::string>> HistogramsNameMap = {
|
|
{DB_GET, "rocksdb.db.get.micros"},
|
|
{DB_WRITE, "rocksdb.db.write.micros"},
|
|
{COMPACTION_TIME, "rocksdb.compaction.times.micros"},
|
|
{COMPACTION_CPU_TIME, "rocksdb.compaction.times.cpu_micros"},
|
|
{SUBCOMPACTION_SETUP_TIME, "rocksdb.subcompaction.setup.times.micros"},
|
|
{TABLE_SYNC_MICROS, "rocksdb.table.sync.micros"},
|
|
{COMPACTION_OUTFILE_SYNC_MICROS, "rocksdb.compaction.outfile.sync.micros"},
|
|
{WAL_FILE_SYNC_MICROS, "rocksdb.wal.file.sync.micros"},
|
|
{MANIFEST_FILE_SYNC_MICROS, "rocksdb.manifest.file.sync.micros"},
|
|
{TABLE_OPEN_IO_MICROS, "rocksdb.table.open.io.micros"},
|
|
{DB_MULTIGET, "rocksdb.db.multiget.micros"},
|
|
{READ_BLOCK_COMPACTION_MICROS, "rocksdb.read.block.compaction.micros"},
|
|
{READ_BLOCK_GET_MICROS, "rocksdb.read.block.get.micros"},
|
|
{WRITE_RAW_BLOCK_MICROS, "rocksdb.write.raw.block.micros"},
|
|
{STALL_L0_SLOWDOWN_COUNT, "rocksdb.l0.slowdown.count"},
|
|
{STALL_MEMTABLE_COMPACTION_COUNT, "rocksdb.memtable.compaction.count"},
|
|
{STALL_L0_NUM_FILES_COUNT, "rocksdb.num.files.stall.count"},
|
|
{HARD_RATE_LIMIT_DELAY_COUNT, "rocksdb.hard.rate.limit.delay.count"},
|
|
{SOFT_RATE_LIMIT_DELAY_COUNT, "rocksdb.soft.rate.limit.delay.count"},
|
|
{NUM_FILES_IN_SINGLE_COMPACTION, "rocksdb.numfiles.in.singlecompaction"},
|
|
{DB_SEEK, "rocksdb.db.seek.micros"},
|
|
{WRITE_STALL, "rocksdb.db.write.stall"},
|
|
{SST_READ_MICROS, "rocksdb.sst.read.micros"},
|
|
{NUM_SUBCOMPACTIONS_SCHEDULED, "rocksdb.num.subcompactions.scheduled"},
|
|
{BYTES_PER_READ, "rocksdb.bytes.per.read"},
|
|
{BYTES_PER_WRITE, "rocksdb.bytes.per.write"},
|
|
{BYTES_PER_MULTIGET, "rocksdb.bytes.per.multiget"},
|
|
{BYTES_COMPRESSED, "rocksdb.bytes.compressed"},
|
|
{BYTES_DECOMPRESSED, "rocksdb.bytes.decompressed"},
|
|
{COMPRESSION_TIMES_NANOS, "rocksdb.compression.times.nanos"},
|
|
{DECOMPRESSION_TIMES_NANOS, "rocksdb.decompression.times.nanos"},
|
|
{READ_NUM_MERGE_OPERANDS, "rocksdb.read.num.merge_operands"},
|
|
{BLOB_DB_KEY_SIZE, "rocksdb.blobdb.key.size"},
|
|
{BLOB_DB_VALUE_SIZE, "rocksdb.blobdb.value.size"},
|
|
{BLOB_DB_WRITE_MICROS, "rocksdb.blobdb.write.micros"},
|
|
{BLOB_DB_GET_MICROS, "rocksdb.blobdb.get.micros"},
|
|
{BLOB_DB_MULTIGET_MICROS, "rocksdb.blobdb.multiget.micros"},
|
|
{BLOB_DB_SEEK_MICROS, "rocksdb.blobdb.seek.micros"},
|
|
{BLOB_DB_NEXT_MICROS, "rocksdb.blobdb.next.micros"},
|
|
{BLOB_DB_PREV_MICROS, "rocksdb.blobdb.prev.micros"},
|
|
{BLOB_DB_BLOB_FILE_WRITE_MICROS, "rocksdb.blobdb.blob.file.write.micros"},
|
|
{BLOB_DB_BLOB_FILE_READ_MICROS, "rocksdb.blobdb.blob.file.read.micros"},
|
|
{BLOB_DB_BLOB_FILE_SYNC_MICROS, "rocksdb.blobdb.blob.file.sync.micros"},
|
|
{BLOB_DB_GC_MICROS, "rocksdb.blobdb.gc.micros"},
|
|
{BLOB_DB_COMPRESSION_MICROS, "rocksdb.blobdb.compression.micros"},
|
|
{BLOB_DB_DECOMPRESSION_MICROS, "rocksdb.blobdb.decompression.micros"},
|
|
{FLUSH_TIME, "rocksdb.db.flush.micros"},
|
|
{SST_BATCH_SIZE, "rocksdb.sst.batch.size"},
|
|
};
|
|
|
|
std::shared_ptr<Statistics> CreateDBStatistics() {
|
|
return std::make_shared<StatisticsImpl>(nullptr);
|
|
}
|
|
|
|
StatisticsImpl::StatisticsImpl(std::shared_ptr<Statistics> stats)
|
|
: stats_(std::move(stats)) {}
|
|
|
|
StatisticsImpl::~StatisticsImpl() {}
|
|
|
|
uint64_t StatisticsImpl::getTickerCount(uint32_t tickerType) const {
|
|
MutexLock lock(&aggregate_lock_);
|
|
return getTickerCountLocked(tickerType);
|
|
}
|
|
|
|
uint64_t StatisticsImpl::getTickerCountLocked(uint32_t tickerType) const {
|
|
assert(tickerType < TICKER_ENUM_MAX);
|
|
uint64_t res = 0;
|
|
for (size_t core_idx = 0; core_idx < per_core_stats_.Size(); ++core_idx) {
|
|
res += per_core_stats_.AccessAtCore(core_idx)->tickers_[tickerType];
|
|
}
|
|
return res;
|
|
}
|
|
|
|
void StatisticsImpl::histogramData(uint32_t histogramType,
|
|
HistogramData* const data) const {
|
|
MutexLock lock(&aggregate_lock_);
|
|
getHistogramImplLocked(histogramType)->Data(data);
|
|
}
|
|
|
|
std::unique_ptr<HistogramImpl> StatisticsImpl::getHistogramImplLocked(
|
|
uint32_t histogramType) const {
|
|
assert(histogramType < HISTOGRAM_ENUM_MAX);
|
|
std::unique_ptr<HistogramImpl> res_hist(new HistogramImpl());
|
|
for (size_t core_idx = 0; core_idx < per_core_stats_.Size(); ++core_idx) {
|
|
res_hist->Merge(
|
|
per_core_stats_.AccessAtCore(core_idx)->histograms_[histogramType]);
|
|
}
|
|
return res_hist;
|
|
}
|
|
|
|
std::string StatisticsImpl::getHistogramString(uint32_t histogramType) const {
|
|
MutexLock lock(&aggregate_lock_);
|
|
return getHistogramImplLocked(histogramType)->ToString();
|
|
}
|
|
|
|
void StatisticsImpl::setTickerCount(uint32_t tickerType, uint64_t count) {
|
|
{
|
|
MutexLock lock(&aggregate_lock_);
|
|
setTickerCountLocked(tickerType, count);
|
|
}
|
|
if (stats_ && tickerType < TICKER_ENUM_MAX) {
|
|
stats_->setTickerCount(tickerType, count);
|
|
}
|
|
}
|
|
|
|
void StatisticsImpl::setTickerCountLocked(uint32_t tickerType, uint64_t count) {
|
|
assert(tickerType < TICKER_ENUM_MAX);
|
|
for (size_t core_idx = 0; core_idx < per_core_stats_.Size(); ++core_idx) {
|
|
if (core_idx == 0) {
|
|
per_core_stats_.AccessAtCore(core_idx)->tickers_[tickerType] = count;
|
|
} else {
|
|
per_core_stats_.AccessAtCore(core_idx)->tickers_[tickerType] = 0;
|
|
}
|
|
}
|
|
}
|
|
|
|
uint64_t StatisticsImpl::getAndResetTickerCount(uint32_t tickerType) {
|
|
uint64_t sum = 0;
|
|
{
|
|
MutexLock lock(&aggregate_lock_);
|
|
assert(tickerType < TICKER_ENUM_MAX);
|
|
for (size_t core_idx = 0; core_idx < per_core_stats_.Size(); ++core_idx) {
|
|
sum +=
|
|
per_core_stats_.AccessAtCore(core_idx)->tickers_[tickerType].exchange(
|
|
0, std::memory_order_relaxed);
|
|
}
|
|
}
|
|
if (stats_ && tickerType < TICKER_ENUM_MAX) {
|
|
stats_->setTickerCount(tickerType, 0);
|
|
}
|
|
return sum;
|
|
}
|
|
|
|
void StatisticsImpl::recordTick(uint32_t tickerType, uint64_t count) {
|
|
assert(tickerType < TICKER_ENUM_MAX);
|
|
per_core_stats_.Access()->tickers_[tickerType].fetch_add(
|
|
count, std::memory_order_relaxed);
|
|
if (stats_ && tickerType < TICKER_ENUM_MAX) {
|
|
stats_->recordTick(tickerType, count);
|
|
}
|
|
}
|
|
|
|
void StatisticsImpl::recordInHistogram(uint32_t histogramType, uint64_t value) {
|
|
assert(histogramType < HISTOGRAM_ENUM_MAX);
|
|
if (get_stats_level() <= StatsLevel::kExceptHistogramOrTimers) {
|
|
return;
|
|
}
|
|
per_core_stats_.Access()->histograms_[histogramType].Add(value);
|
|
if (stats_ && histogramType < HISTOGRAM_ENUM_MAX) {
|
|
stats_->recordInHistogram(histogramType, value);
|
|
}
|
|
}
|
|
|
|
Status StatisticsImpl::Reset() {
|
|
MutexLock lock(&aggregate_lock_);
|
|
for (uint32_t i = 0; i < TICKER_ENUM_MAX; ++i) {
|
|
setTickerCountLocked(i, 0);
|
|
}
|
|
for (uint32_t i = 0; i < HISTOGRAM_ENUM_MAX; ++i) {
|
|
for (size_t core_idx = 0; core_idx < per_core_stats_.Size(); ++core_idx) {
|
|
per_core_stats_.AccessAtCore(core_idx)->histograms_[i].Clear();
|
|
}
|
|
}
|
|
return Status::OK();
|
|
}
|
|
|
|
namespace {
|
|
|
|
// a buffer size used for temp string buffers
|
|
const int kTmpStrBufferSize = 200;
|
|
|
|
} // namespace
|
|
|
|
std::string StatisticsImpl::ToString() const {
|
|
MutexLock lock(&aggregate_lock_);
|
|
std::string res;
|
|
res.reserve(20000);
|
|
for (const auto& t : TickersNameMap) {
|
|
assert(t.first < TICKER_ENUM_MAX);
|
|
char buffer[kTmpStrBufferSize];
|
|
snprintf(buffer, kTmpStrBufferSize, "%s COUNT : %" PRIu64 "\n",
|
|
t.second.c_str(), getTickerCountLocked(t.first));
|
|
res.append(buffer);
|
|
}
|
|
for (const auto& h : HistogramsNameMap) {
|
|
assert(h.first < HISTOGRAM_ENUM_MAX);
|
|
char buffer[kTmpStrBufferSize];
|
|
HistogramData hData;
|
|
getHistogramImplLocked(h.first)->Data(&hData);
|
|
// don't handle failures - buffer should always be big enough and arguments
|
|
// should be provided correctly
|
|
int ret =
|
|
snprintf(buffer, kTmpStrBufferSize,
|
|
"%s P50 : %f P95 : %f P99 : %f P100 : %f COUNT : %" PRIu64
|
|
" SUM : %" PRIu64 "\n",
|
|
h.second.c_str(), hData.median, hData.percentile95,
|
|
hData.percentile99, hData.max, hData.count, hData.sum);
|
|
if (ret < 0 || ret >= kTmpStrBufferSize) {
|
|
assert(false);
|
|
continue;
|
|
}
|
|
res.append(buffer);
|
|
}
|
|
res.shrink_to_fit();
|
|
return res;
|
|
}
|
|
|
|
bool StatisticsImpl::getTickerMap(
|
|
std::map<std::string, uint64_t>* stats_map) const {
|
|
assert(stats_map);
|
|
if (!stats_map) return false;
|
|
stats_map->clear();
|
|
MutexLock lock(&aggregate_lock_);
|
|
for (const auto& t : TickersNameMap) {
|
|
assert(t.first < TICKER_ENUM_MAX);
|
|
(*stats_map)[t.second.c_str()] = getTickerCountLocked(t.first);
|
|
}
|
|
return true;
|
|
}
|
|
|
|
bool StatisticsImpl::HistEnabledForType(uint32_t type) const {
|
|
return type < HISTOGRAM_ENUM_MAX;
|
|
}
|
|
|
|
} // namespace ROCKSDB_NAMESPACE
|